tickiti-mcp
An MCP server that exposes the Tickiti helpdesk API to AI assistants, enabling ticket management and helpdesk operations via natural language.
README
tickiti-mcp
An MCP (Model Context Protocol) server that exposes the
Tickiti helpdesk API to AI assistants such as Claude. It is a thin shim over the
Tickiti Public API v1 (/api/v1/...): each MCP tool forwards to a v1 endpoint, adding
your bearer token and — for writes — an idempotency key. The token's abilities are the
security boundary: the server only relays calls, it never widens them, so a read-only token
gives a read-only assistant.
📖 Full documentation: https://docs.tickiti.com/topic/mcp_server/
Tools
The ticket tools have full, validated inputs; the rest of the API is reachable through two general tools, so the whole surface is available without a separate tool per endpoint.
| Tool | Ability | Purpose |
|---|---|---|
create_ticket |
tickets:write |
Open a ticket (subject+content, template, or intervention) |
respond_to_ticket |
tickets:write |
Post a response to an existing ticket |
query_tickets |
tickets:read |
List tickets for a perspective |
list_perspectives |
settings:read |
List saved perspectives |
list_watchlists |
settings:read |
List watchlists |
list_stock_responses |
settings:read |
List stock responses |
list_queues |
workflow:read |
List ticket queues |
list_workflow |
workflow:read |
List resolution categories, interventions or escalations |
run_report |
reports:read |
Run an analytics report |
list_endpoints |
— | Discover every available API endpoint, with abilities and parameters |
tickiti_call |
per endpoint | Call any /api/v1 endpoint by family and action |
For anything beyond the named tools (mail, templates, workflow writes, administration,
supervisor), the assistant uses list_endpoints to discover the action, then tickiti_call
to run it — covering all of the v1 API.
Requirements
- Node.js 20 or newer
- A Tickiti API token, minted from Administration → API keys, scoped to the abilities you want the assistant to have
- An MCP-capable client — e.g. Claude Code or the Claude desktop app
Install
git clone https://github.com/tickiti/tickiti-mcp.git
cd tickiti-mcp
npm install
npm run build
The built server is dist/server.js.
Configure
The server reads two environment variables (it fails fast on startup if either is missing):
| Variable | Purpose |
|---|---|
TICKITI_API_BASE |
Your Tickiti install's public address, no trailing slash — e.g. https://support.example.com. The server appends /api/v1/…. |
TICKITI_API_TOKEN |
The bearer token. Its abilities determine what the assistant can do. |
Use with Claude Code
claude mcp add tickiti \
--env TICKITI_API_BASE=https://support.example.com \
--env TICKITI_API_TOKEN=YOUR_TICKITI_API_TOKEN \
-- node /absolute/path/to/tickiti-mcp/dist/server.js
Confirm with claude mcp list (or /mcp in a session). Remove with claude mcp remove tickiti.
Other MCP clients configure servers in their own settings file, but the shape is the same:
run node /absolute/path/to/tickiti-mcp/dist/server.js as a stdio server with
TICKITI_API_BASE and TICKITI_API_TOKEN set in its environment.
Permissions & security
The server adds no permissions of its own. Every call runs as the staff user the token belongs to, gated by the token's abilities — exactly as a direct API call would be. To limit what an assistant can do, mint a narrowly-scoped token:
- A read-only token (e.g.
tickets:read,reports:read) gives an assistant that can look but not change anything. - Grant write abilities only for the families the assistant needs to act on.
- If a call is refused, the server reports the reason (missing ability, role or plan).
The two ticket-writing tools send an idempotency key with every call, so a retried request never creates a duplicate ticket or response.
How it works
| File | Role |
|---|---|
src/client.ts |
Request core: base URL, bearer auth, idempotency, error normalisation |
src/result.ts |
Maps an API result into the MCP tool-result envelope |
src/manifest.ts |
Helpers over the generated route manifest (lookup, path building) |
src/generated/manifest.ts |
Auto-generated route table (do not edit) |
src/tools/tickets.ts |
Tickets family — verified input schemas |
src/tools/reads.ts |
Named read tools (settings / workflow / reports) |
src/tools/generic.ts |
list_endpoints + tickiti_call |
src/server.ts |
Entry point: registers tools, connects the stdio transport |
scripts/build-manifest.mjs |
Regenerates the manifest from the Tickiti route table |
Maintainers
src/generated/manifest.ts is generated from Tickiti's own route table
(php artisan route:list --json), so abilities, roles, plan gates and path params are never
hand-maintained. Regenerate against a Tickiti checkout after the API changes:
TICKITI_DIR=/path/to/tickiti npm run manifest
There is an end-to-end sweep over every endpoint in tests/all-paths.mjs
(npm run test:paths, needs a base URL and a full-ability token against a scratch instance).
License
MIT © Oxenic
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。